PulseAugur
EN
LIVE 00:07:31

AI startup Mindgard finds flaw in ChatGPT's safety filters

By PulseAugur Editorial · [1 sources] ·

A British AI security startup, Mindgard, has found a way to bypass ChatGPT's safety filters. By instructing the model to describe an image that is not provided, users can trick ChatGPT into generating inappropriate content. AI

IMPACT Highlights ongoing challenges in AI safety and content moderation, potentially requiring further updates to model guardrails.

RANK_REASON Discovery of a vulnerability in a widely used AI product.

Read on Mastodon — mastodon.social →

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →

AI startup Mindgard finds flaw in ChatGPT's safety filters

How we ranked this

Signal score
0 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
Discovery of a vulnerability in a widely used AI product.
Source corroboration
Single-source cluster
Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics
safety, product
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
87 days old
Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.

Full methodology in our editorial standards.

COVERAGE [1]

  1. Mastodon — mastodon.social TIER_1 English(EN) · [email protected] ·

    So, the gang at # Mindgard , a British # AI security startup, discovered that you can break # ChatGPT by not uploading a picture and telling it to describe the

    So, the gang at # Mindgard , a British # AI security startup, discovered that you can break # ChatGPT by not uploading a picture and telling it to describe the picture you did not upload. Yes, that sounds a little nuts, but it works. I’ve tested it. (The prompt is more complicate…

    LINKS mindgard.ai/…/chatgpt-spontaneously-gener…

RELATED ENTITIES

RELATED TOPICS